{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KDJITFRCVSQTRDTT3OFIXQKOGY","short_pith_number":"pith:KDJITFRC","canonical_record":{"source":{"id":"2302.00808","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6684c559ed46bf3365e7b7e381507338787c857b5ed46d223c53bdee2583953","abstract_canon_sha256":"734afa8906bae8b59fa234cdd0aef9e06c0923532f0132b0eb6809169fb840b8"},"schema_version":"1.0"},"canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","source":{"kind":"arxiv","id":"2302.00808","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00808","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00808v4","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00808","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"KDJITFRCVSQT","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_16","alias_value":"KDJITFRCVSQTRDTT","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_8","alias_value":"KDJITFRC","created_at":"2026-07-05T08:22:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KDJITFRCVSQTRDTT3OFIXQKOGY","target":"record","payload":{"canonical_record":{"source":{"id":"2302.00808","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6684c559ed46bf3365e7b7e381507338787c857b5ed46d223c53bdee2583953","abstract_canon_sha256":"734afa8906bae8b59fa234cdd0aef9e06c0923532f0132b0eb6809169fb840b8"},"schema_version":"1.0"},"canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:30.844027Z","signature_b64":"fEkcHY8BskOfMJ89mSKBhsBvGZwkpLUICTU4T99zfH01KhHOAGAmSMj0hIIGBKw9d1JhXztuxadxBg8A83CAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","last_reissued_at":"2026-07-05T08:22:30.843500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:30.843500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.00808","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:22:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LpKWnFnkMKRxF6Ww5dopkCM3wSc0Bg73CzhQbzTfKC/aIcIokgSm7Q8A8ZRW97zGlxIBgUQZk++yn273225MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:56:58.681429Z"},"content_sha256":"6cfd2f75bdf8517b83296621a4693326feed2d2b89bb893c8420f319a6cdd03b","schema_version":"1.0","event_id":"sha256:6cfd2f75bdf8517b83296621a4693326feed2d2b89bb893c8420f319a6cdd03b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KDJITFRCVSQTRDTT3OFIXQKOGY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akhil Agnihotri, Haipeng Luo, Rahul Jain","submitted_at":"2023-02-02T00:23:36Z","abstract_excerpt":"Reinforcement Learning (RL) for constrained MDPs (CMDPs) is an increasingly important problem for various applications. Often, the average criterion is more suitable than the discounted criterion. Yet, RL for average-CMDPs (ACMDPs) remains a challenging problem. Algorithms designed for discounted constrained RL problems often do not perform well for the average CMDP setting. In this paper, we introduce a new policy optimization with function approximation algorithm for constrained MDPs with the average criterion. The Average-Constrained Policy Optimization (ACPO) algorithm is inspired by trust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00808","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.00808/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:22:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f7FTLy3sKoCCbtYmIrkGzXhe3bFK+N8OwChaX5TDm1kKF9lA2sX1YqBtsImP4ShTn5Fel6iWlCF86I5MxFrHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:56:58.682321Z"},"content_sha256":"544bb69b10008ed2b4a90b332300068c626963a616828d81da610a17e53c59fe","schema_version":"1.0","event_id":"sha256:544bb69b10008ed2b4a90b332300068c626963a616828d81da610a17e53c59fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/bundle.json","state_url":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T18:56:58Z","links":{"resolver":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY","bundle":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/bundle.json","state":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KDJITFRCVSQTRDTT3OFIXQKOGY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"734afa8906bae8b59fa234cdd0aef9e06c0923532f0132b0eb6809169fb840b8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","title_canon_sha256":"d6684c559ed46bf3365e7b7e381507338787c857b5ed46d223c53bdee2583953"},"schema_version":"1.0","source":{"id":"2302.00808","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00808","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00808v4","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00808","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"KDJITFRCVSQT","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_16","alias_value":"KDJITFRCVSQTRDTT","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_8","alias_value":"KDJITFRC","created_at":"2026-07-05T08:22:30Z"}],"graph_snapshots":[{"event_id":"sha256:544bb69b10008ed2b4a90b332300068c626963a616828d81da610a17e53c59fe","target":"graph","created_at":"2026-07-05T08:22:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.00808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) for constrained MDPs (CMDPs) is an increasingly important problem for various applications. Often, the average criterion is more suitable than the discounted criterion. Yet, RL for average-CMDPs (ACMDPs) remains a challenging problem. Algorithms designed for discounted constrained RL problems often do not perform well for the average CMDP setting. In this paper, we introduce a new policy optimization with function approximation algorithm for constrained MDPs with the average criterion. The Average-Constrained Policy Optimization (ACPO) algorithm is inspired by trust","authors_text":"Akhil Agnihotri, Haipeng Luo, Rahul Jain","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00808","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6cfd2f75bdf8517b83296621a4693326feed2d2b89bb893c8420f319a6cdd03b","target":"record","created_at":"2026-07-05T08:22:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"734afa8906bae8b59fa234cdd0aef9e06c0923532f0132b0eb6809169fb840b8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","title_canon_sha256":"d6684c559ed46bf3365e7b7e381507338787c857b5ed46d223c53bdee2583953"},"schema_version":"1.0","source":{"id":"2302.00808","kind":"arxiv","version":4}},"canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","first_computed_at":"2026-07-05T08:22:30.843500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:30.843500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fEkcHY8BskOfMJ89mSKBhsBvGZwkpLUICTU4T99zfH01KhHOAGAmSMj0hIIGBKw9d1JhXztuxadxBg8A83CAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:30.844027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.00808","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cfd2f75bdf8517b83296621a4693326feed2d2b89bb893c8420f319a6cdd03b","sha256:544bb69b10008ed2b4a90b332300068c626963a616828d81da610a17e53c59fe"],"state_sha256":"9fe61b6877c6ffc5c9087f5f1a978f9c2d412b13ea9fce07e27c463be3a9c45d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SU7V815u2LTZDQPo3DkWtowURmB5oz2B6PIt6208msZFTdcETBin2/m3WrEDclfhMJ6W4Fvt8oIizIIa5A8yDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:56:58.687398Z","bundle_sha256":"5c6e152409385f779d9db4215b34a2a2df53acef86177366e087f690e8ad6377"}}